© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11484
    Prev
    Next
    INDEX
    Explanations

    binary sequences as well as specific words in uppercase

    oai_token-act-pair · gpt-3.5-turbo

    specific capitalized words and acronyms, likely related to locations or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crunch
    -0.70
    NPR
    -0.70
    代
    -0.65
    IDENT
    -0.64
    VIDEO
    -0.61
     AMERICA
    -0.60
    FIX
    -0.60
     incub
    -0.59
    RESULTS
    -0.58
     grading
    -0.57
    POSITIVE LOGITS
    tein
    0.99
    fen
    0.80
    glers
    0.76
    phia
    0.75
    ilts
    0.75
    levard
    0.74
    lain
    0.71
    dit
    0.71
    otte
    0.70
    tu
    0.69
    Activations Density 0.185%

    No Known Activations